Ready Policy One: World Building Through Active Learning
12. července 2020
Řečníci
Jack Parker-Holder
Řečník · 1 sledující
Aldo Pacchiano
Řečník · 0 sledujících
Krzysztof Choromanski
Řečník · 0 sledujících
Philip J. Ball
Řečník · 0 sledujících
Stephen J. Roberts
Řečník · 0 sledujících
O prezentaci
Model-Based Reinforcement Learning (MBRL) offers a promising direction for sample efficient learning, often achieving state of the art results for continuous control tasks. However many existing MBRL methods rely on combining greedy policies with exploration heuristics, and even those which utilize principled exploration bonuses construct dual objectives in an ad hoc fashion. In this paper we introduce Ready Policy One (RP1), a framework that views MBRL as an active learning problem, where we aim to improve the world model in the fewest samples possible. RP1 achieves this by utilizing a hybrid objective function, which crucially adapts during optimization, allowing the algorithm to trade off reward v.s. exploration at different stages of learning. In addition, we introduce a principled mechanism to terminate sample collection once we have a rich enough trajectory batch to improve the model. We rigorously evaluate our method on a variety of continuous control tasks, and demonstrate statistically significant gains over existing approaches.Model-Based Reinforcement Learning (MBRL) offers a promising direction for sample efficient learning, often achieving state of the art results for continuous control tasks. However many existing MBRL methods rely on combining greedy policies with exploration heuristics, and even those which utilize principled exploration bonuses construct dual objectives in an ad hoc fashion. In this paper we introduce Ready Policy One (RP1), a framework that views MBRL as an active learning problem, where we ai…
Kategorie
Umělá inteligence a data science
Kategorie · 10,8k prezentací
O organizátorovi (ICML 2020)
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
A system for crowd counting in highly congested scenes geared towards smart transportation system
Zhlédnout později
Machine Learning with Signal Processing - Part II: Stochastic Differential Equations
Zhlédnout později
Thompson Sampling via Local Uncertainty
Zhlédnout později
SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates
Zhlédnout později
Lingkai Kong, …
Novel Audio Embeddings for Personalized Recommendations on Newly Released Tracks
Zhlédnout později
Beici Liang, …
Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation
Zhlédnout později
Yaqi Duan, …